Sandbox Reset

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the destructive/idempotent profile is covered structurally. The description does add real value by naming the destroyed resources and the re-granted $1000 credit, plus the auth requirement. However, much of the behavioral payload overlaps with what the annotations already convey, so this sits at a solid but not exceptional level.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The 'SANDBOX ONLY' warning is front-loaded, and the three sentences each earn their place: scope of destruction, auth precondition, and live-key exclusion. No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no parameters, no output schema, and annotations covering the safety profile, the description supplies everything an agent needs: what is destroyed, what is restored, and the key type required. Nothing material is left unexplained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero input parameters, so the baseline is 4. The description correctly implies no caller-supplied arguments are needed, and nothing is misrepresented or missing from the parameter picture.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (wipe/reset) and resource (sandbox account simulated state), enumerating exactly what is affected: domains, DNS, orders, credit. It is clearly distinguished from siblings like sandbox_topup or create_sandbox_key by its whole-account reset scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives the when ('a clean slate between test runs'), the precondition ('requires a sandbox API key pk1_sb_…'), and the negative case ('with a live key this endpoint is not available'). The agent knows exactly when this tool applies and when it does not.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.